Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization

Shashi Narayan, Shay Cohen, Maria Lapata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling approach. The idea is to create a short, one- sentence news summary answering the question “What is the article about?”. We collect a real-world, large scale dataset for this task by harvesting online articles from the British Broadcasting Corporation (BBC). We propose a novel abstractive model which is conditioned on the article’s topics and based entirely on convolutional neural networks. We demonstrate experimentally that this architecture captures long-range  dependencies in a document and recognizes pertinent content, outperforming an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans.1

1: Our dataset, code, and demo are available at:https://github.com/shashiongithub/XSum.
Original languageEnglish
Title of host publicationProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Place of PublicationBrussels, Belgium
PublisherAssociation for Computational Linguistics
Pages1797-1807
Number of pages11
Publication statusPublished - Nov 2018
Event2018 Conference on Empirical Methods in Natural Language Processing - Square Meeting Center, Brussels, Belgium
Duration: 31 Oct 20184 Nov 2018
http://emnlp2018.org/

Conference

Conference2018 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2018
CountryBelgium
CityBrussels
Period31/10/184/11/18
Internet address

Fingerprint Dive into the research topics of 'Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization'. Together they form a unique fingerprint.

Cite this